conserve

Shapes turns action-first: action leads, steps numbered, state restated. Use for ADHD-friendly output. Do not use to trim tokens; use response-compression.

Tracks per-agent token usage and flags waste in parallel dispatch. Use when evaluating parallel agent efficiency or after a multi-agent run.

Detects codebase bloat via dead code, duplication, complexity, and doc bloat scans. Use when codebase feels large or before a release.

Manages context overflow by handing off to a fresh subagent at 80% usage. Use when context pressure is critical and work must continue uninterrupted.

Applies KISS, YAGNI, and SOLID principles for clean code with reduced complexity. Use when refactoring or reviewing code for over-engineering.

Optimizes context window via MECW principles and memory tiering. Use when context exceeds 30% or before long multi-step tasks.

Establishes CPU/GPU baselines before resource-intensive operations. Use before builds, training runs, or any task that pins cores or GPUs for over a minute.

Guides when to ask clarifying questions versus proceed autonomously. Use to reduce unnecessary clarifying questions when intent is clear.

Guide minimal code via a decision ladder with full safety, edge, and negative-case coverage. Use when adding code, choosing a dependency, or auditing a diff.

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

Compresses verbose responses by removing filler and framing to save 200-400 tokens. Use when responses feel bloated or context is filling fast.

Enforces token quota management at session start with conservation and compression checks. Use at the start of every session or before large context loads.